src/plugin/parse-html/src/java/org/apache/nutch/parse/html/DOMBuilder.java [350:774]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    m_elemStack.pop();
    m_currentNode = m_elemStack.isEmpty() ? null : (Node) m_elemStack.peek();
  }

  /**
   * Set an ID string to node association in the ID table.
   * 
   * @param id
   *          The ID string.
   * @param elem
   *          The associated ID.
   */
  public void setIDAttribute(String id, Element elem) {

    // Do nothing. This method is meant to be overiden.
  }

  /**
   * Receive notification of character data.
   * 
   * <p>
   * The Parser will call this method to report each chunk of character data.
   * SAX parsers may return all contiguous character data in a single chunk, or
   * they may split it into several chunks; however, all of the characters in
   * any single event must come from the same external entity, so that the
   * Locator provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * <p>
   * Note that some parsers will report whitespace using the
   * ignorableWhitespace() method rather than this one (validating parsers must
   * do so).
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #ignorableWhitespace
   * @see org.xml.sax.Locator
   */
  public void characters(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    if (m_inCData) {
      cdata(ch, start, length);

      return;
    }

    String s = new String(ch, start, length);
    Node childNode;
    childNode = m_currentNode != null ? m_currentNode.getLastChild() : null;
    if (childNode != null && childNode.getNodeType() == Node.TEXT_NODE) {
      ((Text) childNode).appendData(s);
    } else {
      Text text = m_doc.createTextNode(s);
      append(text);
    }
  }

  /**
   * If available, when the disable-output-escaping attribute is used, output
   * raw text without escaping. A PI will be inserted in front of the node with
   * the name "lotusxsl-next-is-raw" and a value of "formatter-to-dom".
   * 
   * @param ch
   *          Array containing the characters
   * @param start
   *          Index to start of characters in the array
   * @param length
   *          Number of characters in the array
   * @throws org.xml.sax.SAXException if text is found before 
   * the document element
   */
  public void charactersRaw(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    append(m_doc.createProcessingInstruction("xslt-next-is-raw",
        "formatter-to-dom"));
    append(m_doc.createTextNode(s));
  }

  /**
   * Report the beginning of an entity.
   * 
   * The start and end of the document entity are not reported. The start and
   * end of the external DTD subset are reported using the pseudo-name "[dtd]".
   * All other events must be properly nested within start/end entity events.
   * 
   * @param name
   *          The name of the entity. If it is a parameter entity, the name will
   *          begin with '%'.
   * @see #endEntity
   * @see org.xml.sax.ext.DeclHandler#internalEntityDecl
   * @see org.xml.sax.ext.DeclHandler#externalEntityDecl
   */
  public void startEntity(String name) throws org.xml.sax.SAXException {

    // Almost certainly the wrong behavior...
    // entityReference(name);
  }

  /**
   * Report the end of an entity.
   * 
   * @param name
   *          The name of the entity that is ending.
   * @see #startEntity
   * @throws org.xml.sax.SAXException if text is found before 
   * the document element
   */
  public void endEntity(String name) throws org.xml.sax.SAXException {
  }

  /**
   * Receive notivication of a entityReference.
   * 
   * @param name
   *          name of the entity reference
   * @throws org.xml.sax.SAXException if text is found before 
   * the document element
   */
  public void entityReference(String name) throws org.xml.sax.SAXException {
    append(m_doc.createEntityReference(name));
  }

  /**
   * Receive notification of ignorable whitespace in element content.
   * 
   * <p>
   * Validating Parsers must use this method to report each chunk of ignorable
   * whitespace (see the W3C XML 1.0 recommendation, section 2.10):
   * non-validating parsers may also use this method if they are capable of
   * parsing and using content models.
   * </p>
   * 
   * <p>
   * SAX parsers may return all contiguous whitespace in a single chunk, or they
   * may split it into several chunks; however, all of the characters in any
   * single event must come from the same external entity, so that the Locator
   * provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #characters
   */
  public void ignorableWhitespace(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem())
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    append(m_doc.createTextNode(s));
  }

  /**
   * Tell if the current node is outside the document element.
   * 
   * @return true if the current node is outside the document element.
   */
  private boolean isOutsideDocElem() {
    return (null == m_docFrag)
        && m_elemStack.size() == 0
        && (null == m_currentNode || m_currentNode.getNodeType() == Node.DOCUMENT_NODE);
  }

  /**
   * Receive notification of a processing instruction.
   * 
   * <p>
   * The Parser will invoke this method once for each processing instruction
   * found: note that processing instructions may occur before or after the main
   * document element.
   * </p>
   * 
   * <p>
   * A SAX parser should never report an XML declaration (XML 1.0, section 2.8)
   * or a text declaration (XML 1.0, section 4.3.1) using this method.
   * </p>
   * 
   * @param target
   *          The processing instruction target.
   * @param data
   *          The processing instruction data, or null if none was supplied.
   */
  public void processingInstruction(String target, String data)
      throws org.xml.sax.SAXException {
    append(m_doc.createProcessingInstruction(target, data));
  }

  /**
   * Report an XML comment anywhere in the document.
   * 
   * This callback will be used for comments inside or outside the document
   * element, including comments in the external DTD subset (if read).
   * 
   * @param ch
   *          An array holding the characters in the comment.
   * @param start
   *          The starting position in the array.
   * @param length
   *          The number of characters to use from the array.
   */
  public void comment(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    // tagsoup sometimes submits invalid values here
    if (ch == null || start < 0 || length >= (ch.length - start) || length < 0)
      return;
    append(m_doc.createComment(new String(ch, start, length)));
  }

  /** Flag indicating that we are processing a CData section */
  protected boolean m_inCData = false;

  /**
   * Report the start of a CDATA section.
   * 
   * @see #endCDATA
   */
  public void startCDATA() throws org.xml.sax.SAXException {
    m_inCData = true;
    append(m_doc.createCDATASection(""));
  }

  /**
   * Report the end of a CDATA section.
   * 
   * @see #startCDATA
   */
  public void endCDATA() throws org.xml.sax.SAXException {
    m_inCData = false;
  }

  /**
   * Receive notification of cdata.
   * 
   * <p>
   * The Parser will call this method to report each chunk of character data.
   * SAX parsers may return all contiguous character data in a single chunk, or
   * they may split it into several chunks; however, all of the characters in
   * any single event must come from the same external entity, so that the
   * Locator provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * <p>
   * Note that some parsers will report whitespace using the
   * ignorableWhitespace() method rather than this one (validating parsers must
   * do so).
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #ignorableWhitespace
   * @see org.xml.sax.Locator
   * @throws org.xml.sax.SAXException if text is found before 
   * the document element
   */
  public void cdata(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    // XXX ab@apache.org: modified from the original, to accomodate TagSoup.
    Node n = m_currentNode.getLastChild();
    if (n instanceof CDATASection)
      ((CDATASection) n).appendData(s);
    else if (n instanceof Comment)
      ((Comment) n).appendData(s);
  }

  /**
   * Report the start of DTD declarations, if any.
   * 
   * Any declarations are assumed to be in the internal subset unless otherwise
   * indicated.
   * 
   * @param name
   *          The document type name.
   * @param publicId
   *          The declared public identifier for the external DTD subset, or
   *          null if none was declared.
   * @param systemId
   *          The declared system identifier for the external DTD subset, or
   *          null if none was declared.
   * @see #endDTD
   * @see #startEntity
   */
  public void startDTD(String name, String publicId, String systemId)
      throws org.xml.sax.SAXException {

    // Do nothing for now.
  }

  /**
   * Report the end of DTD declarations.
   * 
   * @see #startDTD
   */
  public void endDTD() throws org.xml.sax.SAXException {

    // Do nothing for now.
  }

  /**
   * Begin the scope of a prefix-URI Namespace mapping.
   * 
   * <p>
   * The information from this event is not necessary for normal Namespace
   * processing: the SAX XML reader will automatically replace prefixes for
   * element and attribute names when the http://xml.org/sax/features/namespaces
   * feature is true (the default).
   * </p>
   * 
   * <p>
   * There are cases, however, when applications need to use prefixes in
   * character data or in attribute values, where they cannot safely be expanded
   * automatically; the start/endPrefixMapping event supplies the information to
   * the application to expand prefixes in those contexts itself, if necessary.
   * </p>
   * 
   * <p>
   * Note that start/endPrefixMapping events are not guaranteed to be properly
   * nested relative to each-other: all startPrefixMapping events will occur
   * before the corresponding startElement event, and all endPrefixMapping
   * events will occur after the corresponding endElement event, but their order
   * is not guaranteed.
   * </p>
   * 
   * @param prefix
   *          The Namespace prefix being declared.
   * @param uri
   *          The Namespace URI the prefix is mapped to.
   * @see #endPrefixMapping
   * @see #startElement
   */
  public void startPrefixMapping(String prefix, String uri)
      throws org.xml.sax.SAXException {

    /*
     * // Not sure if this is needed or wanted // Also, it fails in the stree.
     * if((null != m_currentNode) && (m_currentNode.getNodeType() ==
     * Node.ELEMENT_NODE)) { String qname; if(((null != prefix) &&
     * (prefix.length() == 0)) || (null == prefix)) qname = "xmlns"; else qname
     * = "xmlns:"+prefix;
     * 
     * Element elem = (Element)m_currentNode; String val =
     * elem.getAttribute(qname); // Obsolete, should be DOM2...? if(val == null)
     * { elem.setAttributeNS("http://www.w3.org/XML/1998/namespace", qname,
     * uri); } }
     */
  }

  /**
   * End the scope of a prefix-URI mapping.
   * 
   * <p>
   * See startPrefixMapping for details. This event will always occur after the
   * corresponding endElement event, but the order of endPrefixMapping events is
   * not otherwise guaranteed.
   * </p>
   * 
   * @param prefix
   *          The prefix that was being mapping.
   * @see #startPrefixMapping
   * @see #endElement
   */
  public void endPrefixMapping(String prefix) throws org.xml.sax.SAXException {
  }

  /**
   * Receive notification of a skipped entity.
   * 
   * <p>
   * The Parser will invoke this method once for each entity skipped.
   * Non-validating processors may skip entities if they have not seen the
   * declarations (because, for example, the entity was declared in an external
   * DTD subset). All processors may skip external entities, depending on the
   * values of the http://xml.org/sax/features/external-general-entities and the
   * http://xml.org/sax/features/external-parameter-entities properties.
   * </p>
   * 
   * @param name
   *          The name of the skipped entity. If it is a parameter entity, the
   *          name will begin with '%'.
   */
  public void skippedEntity(String name) throws org.xml.sax.SAXException {
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/plugin/parse-tika/src/java/org/apache/nutch/parse/tika/DOMBuilder.java [359:776]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      m_elemStack.pop();
    }
    m_currentNode = m_elemStack.isEmpty() ? null : (Node) m_elemStack.peek();
  }

  /**
   * Set an ID string to node association in the ID table.
   * 
   * @param id
   *          The ID string.
   * @param elem
   *          The associated ID.
   */
  public void setIDAttribute(String id, Element elem) {

    // Do nothing. This method is meant to be overiden.
  }

  /**
   * Receive notification of character data.
   * 
   * <p>
   * The Parser will call this method to report each chunk of character data.
   * SAX parsers may return all contiguous character data in a single chunk, or
   * they may split it into several chunks; however, all of the characters in
   * any single event must come from the same external entity, so that the
   * Locator provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * <p>
   * Note that some parsers will report whitespace using the
   * ignorableWhitespace() method rather than this one (validating parsers must
   * do so).
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #ignorableWhitespace
   * @see org.xml.sax.Locator
   */
  public void characters(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    if (m_inCData) {
      cdata(ch, start, length);

      return;
    }

    String s = new String(ch, start, length);
    Node childNode;
    childNode = m_currentNode != null ? m_currentNode.getLastChild() : null;
    if (childNode != null && childNode.getNodeType() == Node.TEXT_NODE) {
      ((Text) childNode).appendData(s);
    } else {
      Text text = m_doc.createTextNode(s);
      append(text);
    }
  }

  /**
   * If available, when the disable-output-escaping attribute is used, output
   * raw text without escaping. A PI will be inserted in front of the node with
   * the name "lotusxsl-next-is-raw" and a value of "formatter-to-dom".
   * 
   * @param ch
   *          Array containing the characters
   * @param start
   *          Index to start of characters in the array
   * @param length
   *          Number of characters in the array
   */
  public void charactersRaw(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    append(m_doc.createProcessingInstruction("xslt-next-is-raw",
        "formatter-to-dom"));
    append(m_doc.createTextNode(s));
  }

  /**
   * Report the beginning of an entity.
   * 
   * The start and end of the document entity are not reported. The start and
   * end of the external DTD subset are reported using the pseudo-name "[dtd]".
   * All other events must be properly nested within start/end entity events.
   * 
   * @param name
   *          The name of the entity. If it is a parameter entity, the name will
   *          begin with '%'.
   * @see #endEntity
   * @see org.xml.sax.ext.DeclHandler#internalEntityDecl
   * @see org.xml.sax.ext.DeclHandler#externalEntityDecl
   */
  public void startEntity(String name) throws org.xml.sax.SAXException {

    // Almost certainly the wrong behavior...
    // entityReference(name);
  }

  /**
   * Report the end of an entity.
   * 
   * @param name
   *          The name of the entity that is ending.
   * @see #startEntity
   */
  public void endEntity(String name) throws org.xml.sax.SAXException {
  }

  /**
   * Receive notivication of a entityReference.
   * 
   * @param name
   *          name of the entity reference
   */
  public void entityReference(String name) throws org.xml.sax.SAXException {
    append(m_doc.createEntityReference(name));
  }

  /**
   * Receive notification of ignorable whitespace in element content.
   * 
   * <p>
   * Validating Parsers must use this method to report each chunk of ignorable
   * whitespace (see the W3C XML 1.0 recommendation, section 2.10):
   * non-validating parsers may also use this method if they are capable of
   * parsing and using content models.
   * </p>
   * 
   * <p>
   * SAX parsers may return all contiguous whitespace in a single chunk, or they
   * may split it into several chunks; however, all of the characters in any
   * single event must come from the same external entity, so that the Locator
   * provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #characters
   */
  public void ignorableWhitespace(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem())
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    append(m_doc.createTextNode(s));
  }

  /**
   * Tell if the current node is outside the document element.
   * 
   * @return true if the current node is outside the document element.
   */
  private boolean isOutsideDocElem() {
    return (null == m_docFrag)
        && m_elemStack.size() == 0
        && (null == m_currentNode || m_currentNode.getNodeType() == Node.DOCUMENT_NODE);
  }

  /**
   * Receive notification of a processing instruction.
   * 
   * <p>
   * The Parser will invoke this method once for each processing instruction
   * found: note that processing instructions may occur before or after the main
   * document element.
   * </p>
   * 
   * <p>
   * A SAX parser should never report an XML declaration (XML 1.0, section 2.8)
   * or a text declaration (XML 1.0, section 4.3.1) using this method.
   * </p>
   * 
   * @param target
   *          The processing instruction target.
   * @param data
   *          The processing instruction data, or null if none was supplied.
   */
  public void processingInstruction(String target, String data)
      throws org.xml.sax.SAXException {
    append(m_doc.createProcessingInstruction(target, data));
  }

  /**
   * Report an XML comment anywhere in the document.
   * 
   * This callback will be used for comments inside or outside the document
   * element, including comments in the external DTD subset (if read).
   * 
   * @param ch
   *          An array holding the characters in the comment.
   * @param start
   *          The starting position in the array.
   * @param length
   *          The number of characters to use from the array.
   */
  public void comment(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    // tagsoup sometimes submits invalid values here
    if (ch == null || start < 0 || length >= (ch.length - start) || length < 0)
      return;
    append(m_doc.createComment(new String(ch, start, length)));
  }

  /** Flag indicating that we are processing a CData section */
  protected boolean m_inCData = false;

  /**
   * Report the start of a CDATA section.
   * 
   * @see #endCDATA
   */
  public void startCDATA() throws org.xml.sax.SAXException {
    m_inCData = true;
    append(m_doc.createCDATASection(""));
  }

  /**
   * Report the end of a CDATA section.
   * 
   * @see #startCDATA
   */
  public void endCDATA() throws org.xml.sax.SAXException {
    m_inCData = false;
  }

  /**
   * Receive notification of cdata.
   * 
   * <p>
   * The Parser will call this method to report each chunk of character data.
   * SAX parsers may return all contiguous character data in a single chunk, or
   * they may split it into several chunks; however, all of the characters in
   * any single event must come from the same external entity, so that the
   * Locator provides useful information.
   * </p>
   * 
   * <p>
   * The application must not attempt to read from the array outside of the
   * specified range.
   * </p>
   * 
   * <p>
   * Note that some parsers will report whitespace using the
   * ignorableWhitespace() method rather than this one (validating parsers must
   * do so).
   * </p>
   * 
   * @param ch
   *          The characters from the XML document.
   * @param start
   *          The start position in the array.
   * @param length
   *          The number of characters to read from the array.
   * @see #ignorableWhitespace
   * @see org.xml.sax.Locator
   */
  public void cdata(char ch[], int start, int length)
      throws org.xml.sax.SAXException {
    if (isOutsideDocElem()
        && XMLCharacterRecognizer.isWhiteSpace(ch, start, length))
      return; // avoid DOM006 Hierarchy request error

    String s = new String(ch, start, length);

    // XXX ab@apache.org: modified from the original, to accomodate TagSoup.
    Node n = m_currentNode.getLastChild();
    if (n instanceof CDATASection)
      ((CDATASection) n).appendData(s);
    else if (n instanceof Comment)
      ((Comment) n).appendData(s);
  }

  /**
   * Report the start of DTD declarations, if any.
   * 
   * Any declarations are assumed to be in the internal subset unless otherwise
   * indicated.
   * 
   * @param name
   *          The document type name.
   * @param publicId
   *          The declared public identifier for the external DTD subset, or
   *          null if none was declared.
   * @param systemId
   *          The declared system identifier for the external DTD subset, or
   *          null if none was declared.
   * @see #endDTD
   * @see #startEntity
   */
  public void startDTD(String name, String publicId, String systemId)
      throws org.xml.sax.SAXException {

    // Do nothing for now.
  }

  /**
   * Report the end of DTD declarations.
   * 
   * @see #startDTD
   */
  public void endDTD() throws org.xml.sax.SAXException {

    // Do nothing for now.
  }

  /**
   * Begin the scope of a prefix-URI Namespace mapping.
   * 
   * <p>
   * The information from this event is not necessary for normal Namespace
   * processing: the SAX XML reader will automatically replace prefixes for
   * element and attribute names when the http://xml.org/sax/features/namespaces
   * feature is true (the default).
   * </p>
   * 
   * <p>
   * There are cases, however, when applications need to use prefixes in
   * character data or in attribute values, where they cannot safely be expanded
   * automatically; the start/endPrefixMapping event supplies the information to
   * the application to expand prefixes in those contexts itself, if necessary.
   * </p>
   * 
   * <p>
   * Note that start/endPrefixMapping events are not guaranteed to be properly
   * nested relative to each-other: all startPrefixMapping events will occur
   * before the corresponding startElement event, and all endPrefixMapping
   * events will occur after the corresponding endElement event, but their order
   * is not guaranteed.
   * </p>
   * 
   * @param prefix
   *          The Namespace prefix being declared.
   * @param uri
   *          The Namespace URI the prefix is mapped to.
   * @see #endPrefixMapping
   * @see #startElement
   */
  public void startPrefixMapping(String prefix, String uri)
      throws org.xml.sax.SAXException {

    /*
     * // Not sure if this is needed or wanted // Also, it fails in the stree.
     * if((null != m_currentNode) && (m_currentNode.getNodeType() ==
     * Node.ELEMENT_NODE)) { String qname; if(((null != prefix) &&
     * (prefix.length() == 0)) || (null == prefix)) qname = "xmlns"; else qname
     * = "xmlns:"+prefix;
     * 
     * Element elem = (Element)m_currentNode; String val =
     * elem.getAttribute(qname); // Obsolete, should be DOM2...? if(val == null)
     * { elem.setAttributeNS("http://www.w3.org/XML/1998/namespace", qname,
     * uri); } }
     */
  }

  /**
   * End the scope of a prefix-URI mapping.
   * 
   * <p>
   * See startPrefixMapping for details. This event will always occur after the
   * corresponding endElement event, but the order of endPrefixMapping events is
   * not otherwise guaranteed.
   * </p>
   * 
   * @param prefix
   *          The prefix that was being mapping.
   * @see #startPrefixMapping
   * @see #endElement
   */
  public void endPrefixMapping(String prefix) throws org.xml.sax.SAXException {
  }

  /**
   * Receive notification of a skipped entity.
   * 
   * <p>
   * The Parser will invoke this method once for each entity skipped.
   * Non-validating processors may skip entities if they have not seen the
   * declarations (because, for example, the entity was declared in an external
   * DTD subset). All processors may skip external entities, depending on the
   * values of the http://xml.org/sax/features/external-general-entities and the
   * http://xml.org/sax/features/external-parameter-entities properties.
   * </p>
   * 
   * @param name
   *          The name of the skipped entity. If it is a parameter entity, the
   *          name will begin with '%'.
   */
  public void skippedEntity(String name) throws org.xml.sax.SAXException {
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -